© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107756
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tornado
    -0.25
    Meteor
    -0.24
    mát
    -0.23
    ders
    -0.23
     gu
    -0.23
    dź
    -0.23
    (find
    -0.23
    å±ħæ°ij
    -0.23
    ignment
    -0.23
    çĵľ
    -0.23
    POSITIVE LOGITS
    ashi
    0.30
    patch
    0.28
    Release
    0.28
     salute
    0.27
     Release
    0.27
    ìĩĦ
    0.25
    è·£
    0.24
     sæ
    0.24
     Chun
    0.24
    ocr
    0.24
    Activations Density 1.973%

    No Known Activations

    This feature has no known activations.